> For the complete documentation index, see [llms.txt](https://docs.teleskope.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.teleskope.ai/the-platform/kosmo.md).

# Kosmo

{% hint style="info" %}
Kosmo may not be enabled for your organization yet. Contact your Technical Account Manager to enable.
{% endhint %}

## What Is Kosmo?

Kosmo is Teleskope's AI assistant. It answers questions about the data in your Teleskope environment — files, sensitivity classifications, sharing settings, policies, identities, and findings — using natural language. From the same conversation, you can run a triage to prioritize a risk area or build a report with charts and written takeaways.

Kosmo works from your Teleskope metadata: file names and paths, owners and who has access (including email addresses), classifications, sharing settings, findings, and counts. The Kosmo assistant does not receive file contents.

To open Kosmo, click the Kosmo icon at the bottom right of the screen. To browse the full catalog without the chat panel, see [Data Explorer](https://docs.teleskope.ai/the-platform/ai-search.md).

***

## Triage

Triage takes a broad risk question — for example, "Show me our external sharing risk" — and breaks the matching resources into prioritized groups, worst first, each with a count and a recommended action. Large groups may show as "more than N."

What you get back:

* A summary and a single priority action at the top.
* Groups ranked by severity, each with a count and a connector breakdown.
* A recommended action for each group.

***

## Reports

Reports are multi-section documents that Kosmo builds from your data. You can ask for a report on a specific topic and Kosmo assembles it in the conversation.

Each report contains:

* Charts (bar, line, pie).
* Tables.
* Stat cards for key figures.
* Written takeaways summarizing the findings.

Built-in report types include:

* Exposure & Access Risk
* Public Link Risk
* Storage Cost — Archive Candidates
* Stale Sensitive Data
* Missing Document Types
* AI Enablement Readiness
* General Risk Overview
* Records of Processing (RoPA)
* Framework Compliance
* Ghost & Offboarded Access
* Sensitivity Hotspots
* Sensitivity Label Coverage
* Duplicate Data
* Slack Channels
* Policy Findings

What you can do with a report:

* Refresh it against current data.
* Edit or share it, if you created it. Others can view and refresh it.
* Set visibility to Private or Anyone in my organization, and copy a direct link.
* Export it to PDF.
* Choose light or dark appearance with your own logo and colors.

Saved reports are on the **Reports** page in the left navigation.
